dreamina-4-0/text-to-image
Next-gen AI visual tool merging text-driven image creation with precision editing.
Wan 2.7 Pro text-to-image on RunComfy targets higher output fidelity than the standard tier while using the same input fields. Standard and Pro share parameter names so you can move a draft from the non-Pro model to Pro. Confirm exact pixel ceilings against the current RunComfy model limits.
Each run returns an images array with one to five files per request, optional generated_text, and seed in the response.
image_size presets for common aspect buckets; advanced {width, height} objects may be available in custom integrations.max_images 1–5 for controlled variation batches.| Parameter | Required | Type | Default | Range / Options | Description |
|---|---|---|---|---|---|
| prompt* | Yes | string | — | — | Scene, style, lighting, layout. |
| negative_prompt | No | string | "" | max 500 chars | Undesired content. |
| image_size | No | string | square_hd | enum presets | Output size preset. |
| max_images | No | integer | 1 | 1–5 | Images per job. |
| seed | No | integer | — | 0–2147483647 | Repeatability. |
| enable_safety_checker | No | boolean | true | on / off | Moderation. |
| Billing | Rate |
|---|---|
| Per generated image | $0.075 |
Total run cost scales with max_images.
negative_prompt short and specific.image_size preset closest to your deliverable aspect ratio.seed while tweaking wording so you can isolate prompt effects.max_images sparingly on Pro to manage spend.Next-gen AI visual tool merging text-driven image creation with precision editing.
Refine texture, geometry, and lighting with chrono-edit upscaler for realistic image upscaling.
Generate 4K visuals with precise edits and style control for designers.
LoRA-based visual editing model offering structure-aware asset transformation for creative pros
Instruction-based AI for seamless visual editing and scalable style adaptation
Advanced image editing model for detailed, consistent visual creation and precise design workflows.
Wan 2.7 Pro targets higher output fidelity than the standard tier. On RunComfy it costs $0.075 per generated image, while standard is lower for draft work. Both tiers expose the same field names, so you can move a prompt from standard to Pro without relearning controls.
$0.075 per generated image. If you request more than one image in a single job (max_images greater than 1), multiply by the number of images returned.
Yes. Both use prompt, negative_prompt, image_size, max_images, seed, and enable_safety_checker on RunComfy. Quality and list price are what change between tiers.
Pixel ceilings can change when the provider or RunComfy deployment updates. Before you promise a print size, check the current RunComfy model limits or your workspace documentation.
Keep seed fixed while you adjust wording, change one creative variable at a time, and compare outputs. Raise max_images when you want several alternatives from the same settings.
RunComfy is the premier ComfyUI platform, offering ComfyUI online environment and services, along with ComfyUI workflows featuring stunning visuals. RunComfy also provides AI Models, enabling artists to harness the latest AI tools to create incredible art.
